Zero Shot Object Tracking Tutorial

Jacobsolawetz commented 2 years ago

🚀 Feature

Adding a tutorial link to zero shot object tracking

Motivation

Object tracking algorithms like deepsort require you to train a separate featurizer on your object tracks, requiring additional annotation. It would be nice to just show up with your object detection model and get tracking.

Pitch

In the zero shot object tracking, @maxhs2014, @yeldarby and I (mostly @maxhs2014) proved out an object tracking approach that used CLIP features zero shot. No need to train an additional model, you can just show up with your YOLOv5 weights and track objects in a video.

Alternatives

Traditional deepsort for tracking on the edge and more accurate in-domain features

Additional Considerations

We would need to maintain this against YOLOv5 releases - or perhaps call out a particular hash that is supported

glenn-jocher commented 2 years ago

@Jacobsolawetz sounds interesting! What would be next steps?

github-actions[bot] commented 2 years ago

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

Wiki – https://github.com/ultralytics/yolov5/wiki
Tutorials – https://docs.ultralytics.com/yolov5
Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

Ultralytics HUB – https://ultralytics.com/hub
Vision API – https://ultralytics.com/yolov5
About Us – https://ultralytics.com/about
Join Our Team – https://ultralytics.com/work
Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

ultralytics / yolov5